Deep-learning based detection of COVID-19 using lung ultrasound imagery.

BACKGROUND: The COVID-19 pandemic has exposed the vulnerability of healthcare services worldwide, especially in underdeveloped countries. There is a clear need to develop novel computer-assisted diagnosis tools to provide rapid and cost-effective screening in places where massive traditional testing is not feasible. Lung ultrasound is a portable, easy to disinfect, low cost and non-invasive tool that can be used to identify lung diseases. Computer-assisted analysis of lung ultrasound imagery is a relatively recent approach that has shown great potential for diagnosing pulmonary conditions, being a viable alternative for screening and diagnosing COVID-19. OBJECTIVE: To evaluate and compare the performance of deep-learning techniques for detecting COVID-19 infections from lung ultrasound imagery. METHODS: We adapted different pre-trained deep learning architectures, including VGG19, InceptionV3, Xception, and ResNet50. We used the publicly available POCUS dataset comprising 3326 lung ultrasound frames of healthy, COVID-19, and pneumonia patients for training and fine-tuning. We conducted two experiments considering three classes (COVID-19, pneumonia, and healthy) and two classes (COVID-19 versus pneumonia and COVID-19 versus non-COVID-19) of predictive models. The obtained results were also compared with the POCOVID-net model. For performance evaluation, we calculated per-class classification metrics (Precision, Recall, and F1-score) and overall metrics (Accuracy, Balanced Accuracy, and Area Under the Receiver Operating Characteristic Curve). Lastly, we performed a statistical analysis of performance results using ANOVA and Friedman tests followed by post-hoc analysis using the Wilcoxon signed-rank test with the Holm's step-down correction. RESULTS: InceptionV3 network achieved the best average accuracy (89.1%), balanced accuracy (89.3%), and area under the receiver operating curve (97.1%) for COVID-19 detection from bacterial pneumonia and healthy lung ultrasound data. The ANOVA and Friedman tests found statistically significant performance differences between models for accuracy, balanced accuracy and area under the receiver operating curve. Post-hoc analysis showed statistically significant differences between the performance obtained with the InceptionV3-based model and POCOVID-net, VGG19-, and ResNet50-based models. No statistically significant differences were found in the performance obtained with InceptionV3- and Xception-based models. CONCLUSIONS: Deep learning techniques for computer-assisted analysis of lung ultrasound imagery provide a promising avenue for COVID-19 screening and diagnosis. Particularly, we found that the InceptionV3 network provides the most promising predictive results from all AI-based techniques evaluated in this work. InceptionV3- and Xception-based models can be used to further develop a viable computer-assisted screening tool for COVID-19 based on ultrasound imagery.

Design and evaluation of a parametric model for cardiac sounds.

Heart sound analysis plays an important role in the auscultative diagnosis process to detect the presence of cardiovascular diseases. In this paper we propose a novel parametric heart sound model that accurately represents normal and pathological cardiac audio signals, also known as phonocardiograms (PCG). The proposed model considers that the PCG signal is formed by the sum of two parts: one of them is deterministic and the other one is stochastic. The first part contains most of the acoustic energy. This part is modeled by the Matching Pursuit (MP) algorithm, which performs an analysis-synthesis procedure to represent the PCG signal as a linear combination of elementary waveforms. The second part, also called residual, is obtained after subtracting the deterministic signal from the original heart sound recording and can be accurately represented as an autoregressive process using the Linear Predictive Coding (LPC) technique. We evaluate the proposed heart sound model by performing subjective and objective tests using signals corresponding to different pathological cardiac sounds. The results of the objective evaluation show an average Percentage of Root-Mean-Square Difference of approximately 5% between the original heart sound and the reconstructed signal. For the subjective test we conducted a formal methodology for perceptual evaluation of audio quality with the assistance of medical experts. Statistical results of the subjective evaluation show that our model provides a highly accurate approximation of real heart sound signals. We are not aware of any previous heart sound model rigorously evaluated as our proposal.

Reliable multihop broadcast protocol with a low-overhead link quality assessment for ITS based on VANETs in highway scenarios.

Vehicular ad hoc networks (VANETs) have been identified as a key technology to enable intelligent transport systems (ITS), which are aimed to radically improve the safety, comfort, and greenness of the vehicles in the road. However, in order to fully exploit VANETs potential, several issues must be addressed. Because of the high dynamic of VANETs and the impairments in the wireless channel, one key issue arising when working with VANETs is the multihop dissemination of broadcast packets for safety and infotainment applications. In this paper a reliable low-overhead multihop broadcast (RLMB) protocol is proposed to address the well-known broadcast storm problem. The proposed RLMB takes advantage of the hello messages exchanged between the vehicles and it processes such information to intelligently select a relay set and reduce the redundant broadcast. Additionally, to reduce the hello messages rate dependency, RLMB uses a point-to-zone link evaluation approach. RLMB performance is compared with one of the leading multihop broadcast protocols existing to date. Performance metrics show that our RLMB solution outperforms the leading protocol in terms of important metrics such as packet dissemination ratio, overhead, and delay.

Reliable freestanding position-based routing in highway scenarios.

Vehicular Ad Hoc Networks (VANETs) are considered by car manufacturers and the research community as the enabling technology to radically improve the safety, efficiency and comfort of everyday driving. However, before VANET technology can fulfill all its expected potential, several difficulties must be addressed. One key issue arising when working with VANETs is the complexity of the networking protocols compared to those used by traditional infrastructure networks. Therefore, proper design of the routing strategy becomes a main issue for the effective deployment of VANETs. In this paper, a reliable freestanding position-based routing algorithm (FPBR) for highway scenarios is proposed. For this scenario, several important issues such as the high mobility of vehicles and the propagation conditions may affect the performance of the routing strategy. These constraints have only been partially addressed in previous proposals. In contrast, the design approach used for developing FPBR considered the constraints imposed by a highway scenario and implements mechanisms to overcome them. FPBR performance is compared to one of the leading protocols for highway scenarios. Performance metrics show that FPBR yields similar results when considering freespace propagation conditions, and outperforms the leading protocol when considering a realistic highway path loss model.